Vad kan man göra med en nollhypotes?

[Garvarn]

Avknoppat från Behövs folkbildning av VoF-typ? /calle555

Vi är ju i läget att "bevisa 0-hypoteser" nu egentligen. (Vilket enligt sedvanlig statistik inte är möjligt, man kan bara förkasta 0-hypoteser).

Nej, man kan acceptera dem också.

[EvaB]

Vi är ju i läget att "bevisa 0-hypoteser" nu egentligen. (Vilket enligt sedvanlig statistik inte är möjligt, man kan bara förkasta 0-hypoteser).

Nej, man kan acceptera dem också.

Nej, det kan man inte. Man kan bara säga att man inte kan förkasta 0-hypotesen.

Detta kan låta som hårklyveri, men är inte det.

[Garvarn]

Vi är ju i läget att "bevisa 0-hypoteser" nu egentligen. (Vilket enligt sedvanlig statistik inte är möjligt, man kan bara förkasta 0-hypoteser).

Nej, man kan acceptera dem också.

Nej, det kan man inte. Man kan bara säga att man inte kan förkasta 0-hypotesen.

Detta kan låta som hårklyveri, men är inte det.

Tja, enligt metodlitteraturen kan man det.

[EvaB]

Nej, man kan acceptera dem också.

Nej, det kan man inte. Man kan bara säga att man inte kan förkasta 0-hypotesen.
Detta kan låta som hårklyveri, men är inte det.

Tja, enligt metodlitteraturen kan man det.

Ge länk.

[EvaB]

Engelska wiki förklarar det såhär (notera det ställe jag satt in fetstil):

http://en.wikipedia.org/wiki/Null_hypothesis

The null hypothesis (often denoted by H0) formally describes some aspect of the statistical "behaviour" of a set of data. This description is assumed to be valid unless the actual behaviour of the data contradicts this assumption. Thus, the null hypothesis is contrasted against another or alternative hypothesis. Statistical hypothesis testing, which involves a number of steps, is used to decide whether the data contradicts the null hypothesis. This is called significance testing. A null hypothesis is never proven by such methods, as the absence of evidence against the null hypothesis does not establish its truth. In other words, one may either reject, or not reject the null hypothesis; one cannot accept it.

[Garvarn]

Ge länk.

Bättre än så, jag kan referera till den:

Shadish, W.R., Cook, T.D., & Campbell, D.T. (2002). Experimental and quasi-experimental designs for generalized causal inference. Boston: Houghton Mifflin.

McBurney, D.H., & White, T.L. (2007). Research methods. Belmont: Wadsworth.

[EvaB]

Eftersom jag nu inte råkar äga dessa böcker så kan du ju skriva av något litet avsnitt som styrker det du säger.

[Garvarn]

Eftersom jag nu inte råkar äga dessa böcker så kan du ju skriva av något litet avsnitt som styrker det du säger.

Tja, McBurney och White förklarar typ II-fel som "you have accepted the null hypothesis when it is false."

[EvaB]

Eftersom jag nu inte råkar äga dessa böcker så kan du ju skriva av något litet avsnitt som styrker det du säger.

Tja, McBurney och White förklarar typ II-fel som "you have accepted the null hypothesis when it is false."

Vilket nu inte är samma sak.

Klipper från en annan websida på engelska wiki som förklarar bägge delarna samtidigt (markerar med fetstil de aktuella meningarna)

http://en.wikipedia.org/wiki/Statistics


Key terms used in statistics

[edit]Null hypothesis
Interpretation of statistical information can often involve the development of a null hypothesis in that the assumption is that whatever is proposed as a cause has no effect on the variable being measured.
The best illustration for a novice is the predicament encountered by a jury trial. The null hypothesis, H0, asserts that the defendant is innocent, whereas the alternative hypothesis, H1, asserts that the defendant is guilty.
The indictment comes because of suspicion of the guilt. The H0 (status quo) stands in opposition to H1 and is maintained unless H1 is supported by evidence "beyond a reasonable doubt". However, "failure to reject H0" in this case does not imply innocence, but merely that the evidence was insufficient to convict. So the jury does not necessarily accept H0 but fails to reject H0.


[edit]Error
Working from a null hypothesis two basic forms of error are recognised:
Type I errors where the null hypothesis is falsely rejected giving a "false positive".
Type II errors where the null hypothesis fails to be rejected and an actual difference between populations is missed.
[

[Garvarn]

Despite frequent opinions to the contrary, this null hypothesis can be correct in some situations. Appropriate criteria for accepting the null hypothesis are (1) that the null hypothesis is possible; (2) that the results are consistent with the null hypothesis; and (3) that the experiment was a good effort to find an effect. These criteria are consistent with the meta-rules for psychology. The good-effort criterion is subjective, which is somewhat undesirable, but the alternative--never accepting the null hypothesis--is neither desirable nor practical.

[EvaB]

Despite frequent opinions to the contrary, this null hypothesis can be correct in some situations. Appropriate criteria for accepting the null hypothesis are (1) that the null hypothesis is possible; (2) that the results are consistent with the null hypothesis; and (3) that the experiment was a good effort to find an effect. These criteria are consistent with the meta-rules for psychology. The good-effort criterion is subjective, which is somewhat undesirable, but the alternative--never accepting the null hypothesis--is neither desirable nor practical.

can be correct in some situations

Vilket jag ju redan nämnt i samband med Cochrane.

I de flesta situationer kan man dock inte räkna med det.

[kaxiga Z]

Despite frequent opinions to the contrary, this null hypothesis can be correct in some situations. Appropriate criteria for accepting the null hypothesis are (1) that the null hypothesis is possible; (2) that the results are consistent with the null hypothesis; and (3) that the experiment was a good effort to find an effect. These criteria are consistent with the meta-rules for psychology. The good-effort criterion is subjective, which is somewhat undesirable, but the alternative--never accepting the null hypothesis--is neither desirable nor practical.

can be correct in some situations

Vilket jag ju redan nämnt i samband med Cochrane.

I de flesta situationer kan man dock inte räkna med det.

m a o: Det beror på hur stor 'power' den statistiska hypotesen har. (både vad gäller H0 jämfört med H1, och antalet relevanta alternativa hypoteser man testat H0 mot)

[pwm]

Despite frequent opinions to the contrary, this null hypothesis can be correct in some situations. Appropriate criteria for accepting the null hypothesis are (1) that the null hypothesis is possible; (2) that the results are consistent with the null hypothesis; and (3) that the experiment was a good effort to find an effect. These criteria are consistent with the meta-rules for psychology. The good-effort criterion is subjective, which is somewhat undesirable, but the alternative--never accepting the null hypothesis--is neither desirable nor practical.

can be correct in some situations

Vilket jag ju redan nämnt i samband med Cochrane.

I de flesta situationer kan man dock inte räkna med det.

Så man kan acceptera en noll-hypotes.

[EvaB]

Despite frequent opinions to the contrary, this null hypothesis can be correct in some situations. Appropriate criteria for accepting the null hypothesis are (1) that the null hypothesis is possible; (2) that the results are consistent with the null hypothesis; and (3) that the experiment was a good effort to find an effect. These criteria are consistent with the meta-rules for psychology. The good-effort criterion is subjective, which is somewhat undesirable, but the alternative--never accepting the null hypothesis--is neither desirable nor practical.

can be correct in some situations

Vilket jag ju redan nämnt i samband med Cochrane.

I de flesta situationer kan man dock inte räkna med det.

m a o: Det beror på hur stor 'power' den statistiska hypotesen har. (både vad gäller H0 jämfört med H1, och antalet relevanta alternativa hypoteser man testat H0 mot)

Japp, och också att man har vettiga begrepp och mått man jobbar med.

[EvaB]

Despite frequent opinions to the contrary, this null hypothesis can be correct in some situations. Appropriate criteria for accepting the null hypothesis are (1) that the null hypothesis is possible; (2) that the results are consistent with the null hypothesis; and (3) that the experiment was a good effort to find an effect. These criteria are consistent with the meta-rules for psychology. The good-effort criterion is subjective, which is somewhat undesirable, but the alternative--never accepting the null hypothesis--is neither desirable nor practical.

can be correct in some situations

Vilket jag ju redan nämnt i samband med Cochrane.

I de flesta situationer kan man dock inte räkna med det.

Så man kan acceptera en noll-hypotes.